Open main menu

CDOT Wiki β

Changes

Fall 2014 SPO600 Weekly Schedule

1,384 bytes removed, 12:36, 18 November 2014
no edit summary
|-
|4||Sept 22||[[#Tuesday (Sep 23)|Assembly language presentations & Assembly Basics]]||[[#Friday (Sep 26)|Assembly Language Lablanguage presentations, continued]]||[[#Week 4 Deliverables|Blog about writing in assembly language (Lab 3)the content of your presentation]]
|-
|5||Sep 29||[[#Tuesday (Sep 30)|Discuss Assembly lab (Lab 3 results / Inline assembler and compiler optimizations)]]||[[#Friday (Oct 3)|Inline assembler and compiler optimizations / Potential Project Triage – Scan the potential project list from the Linaro Performance site]]||[[#Week 5 Deliverables|Blog post about assembly lab (lab 3) and potential projects]]
|-
|6||Oct 6||[[#Tuesday (Oct 7)|Guest Speaker: Jon "Maddog" Hall]]||[[#Friday (Oct 10)|Codebase analysis||/ Memory barriers and Atomics]]||[[#Week 6 Deliverables|Analyze your portion of the potential projects list and post your results on the wiki and your blog; select two projects and contact the associated communitiesplatform-specific code in 3 packages.]]
|-
|7||Oct 13||[#Tuesday (Oct 15)|[[#Tuesday (Oct 14)|Architecture-specific Code for Performance- Why?]]||Group hack session - Porting[[#Friday (Oct 17)|Compiler Intrinsics and Picking your Package]]||[[#Week 7 Deliverables|Blog Pick your package and blog about your progressit.]]
|-style="background: #f0f0ff"
|Study Week||Oct 20||colspan="3" align="center"|Study Week<br />'''[http://fsoss.ca FSOSS 2014] on Thursday-Friday'''
|-
|8||Oct 27||Architecture-specific [[#Tuesday (Oct 28)|Working with the Code for Performance]]||[[#Friday (Oct 31)|Group hack session - PortingProfiling]]||[[#Week 8 Deliverables|Blog about your progress.]]
|-
|9||Nov 3||Portability - Removing platform-specific code[[#Tuesday (Nov 4)|Profiling review]]||[[#Friday (Nov 11)|Group hack session - Portability]]||[[#Week 9 Deliverables|Blog about Post baseline stats for your progresssoftware.]]
|-
<!--
|810||Nov 10||Project Work[[#Tuesday (Nov 11)|Presentations]]||Project Work[[#Friday (Nov 14)|AArch64 on x86_64 / Hack session]]||[[#Week 10 Deliverables|Get code into review and blog Blog about ityour project status - 1st project marks.]]
|-
|911||Nov 17||Status Update[[#Tuesday (Nov 18)|Discussion and hack session]]|Foundation Models|[[#Friday (Nov 21)|Install Discussion and Test With Foundation Model hack session: Commercial vs. Technical Reality]]||[[#Week 11 Deliverables|Upstream your work and blog about it.]]
|-
-->
|1012||Nov 1024||Profiling[[#Tuesday (Nov 25)|Project Update Presentations]]||[[#Friday (Nov 28)|Discussion and hack session]]|Baseline Profiling|[[#Week 12 Deliverables|Post baseline stats for Blog about your softwareproject status - 2nd project marks.]]
|-
|1113||Nov 17Dec 1||Optimizing Code[[#Tuesday (Dec 2)||Group hack - Profiling Discussion and optimizing||Post a code review update.|- |12||Nov 24||Using complier optimizations||Project Work||Post a code review update.|- |13Hack Session]]||[[#Friday (Dec 15)||Final Presentations||Final PresentationsDiscussion and Hack Session]]||Code accepted upstream. Blog about it!
|-style="background: #f0f0ff"
!Category!!Percentage!!Evaluation Dates
|-
|Communication||align="right"|20%||<strike>September 30</strike>, <strike>October 31</strike>, November 21, December 10
|-
|Quizzes||align="right"|10%||May be held during any class, usually at the start of class. A minimum of 5 one-page quizzes will be given. No make-up/retake option is offered if you miss a quiz. Lowest 3 scores will not be counted.
|Labs||align="right"|10%||See deliverables column above.
|-
|Project work||align="right"|60%||October 10<strike>November 11</strike> (15%), November 2125 (20%), December 10(25%)
|}
=== Tuesday (Sep 23) ===
* Give your [[Fall 2014 SPO600 Assembly Language Presentation|presentation about an assembly language topic]] - teach your SPO600 colleagues
* [[Assembler Basics|Introduction to assembly language]]
=== Friday (Sep 26) ===
* Remainder of the [[Fall 2014 SPO600 Assembly Language Presentation|presentations about an assembly language topic]]
* [[Assembler Basics|Introduction to assembly language]]
* Writing x86_64 and aarch64 code in the [[SPO600 Assembler Lab|Assembly language lab (Lab 3)]]
=== Week 4 Deliverables ===
* Blog about the your [[Fall 2014 SPO600 Assembler LabAssembly Language Presentation|assembler lab (Lab 3)presentation]]
== Week 5 ==
=== Tuesday (Sep 30) ===
* [[SPO600 Assembler Lab|Assembler Lab]] review === Friday (Oct 3) === 
* [[Inline Assembly Language]]
* [[Compiler Optimizations]]
=== Friday (Oct 3) ===The [http://performance.linaro.org/ Linaro Performance Challenge] is a project initiated by [http://en.wikipedia.org/wiki/Jon_Hall_%28programmer%29 Jon "Maddog" Hall] and [http://www.linaro.org Linaro] to port or make portable open source software packages which contain platform-specific code and which may not build on the new Aarch64 architecture.
The (There are two videos about the challenge, both of which are from late 2013 while the program was being finalized: [httphttps://performancewww.linaroyoutube.orgcom/ Linaro Performance Challengewatch?v=Lo1dBB3tke8 One of an interview with Maddog and Steve Macintyre] is a project initiated by , and [http://enpeople.wikipedialinaro.org/wikilinaro-connect/lcu13/videos/10-28-Monday/Jon_Hall_LCU13%20ARM%28programmer20Performance%29 Jon "Maddog" Hall] and [http://www20Optimizations.linaro.org mp4 the other of a LinaroConnect presentation by Maddog] to port or make portable open source software packages which contain platform-specific code and which may not build on the new Aarch64 architecture).
The [http://performance.linaro.org/find/ list of packages] for this project was originally developed by the UK Debian developer Steve Macintyre, who works for Linaro. His focus in developing that list was to find packages that contained assembly language code for x86 (or other platforms) and which did not have assembly language code for ARM, especially Aarch64. As a result, the list includes many false-positives: there are many packages on there that can successfully build on ARM, either due to C work-arounds for the missing assembly code, or conditional compilation of the assembly code, or recent updates to the software, or other reasons.
In this class, we're going to start to triage this list by analyzing which packages exist in the Fedora package set and which have been successfully built for the aarch64 architecture.
This is the approximate plan for this classThe list has been processed with these steps:
# Grab the list of packages from the Linaro Performance Challenge site.
# Find out the corresponding names of the packages in the Fedora package set. Most of these will be the same as in the list, but some may be different.
# Find out which packages have not been built on x86_64# Find out which packages have build for Fedora on aarch64# Come up with a short-list which consists of the packages in these groups:## Packages which do not exist in Fedora -- these need further investigation## Packages which exist in Fedora and build on x86_64, but which do not build on aarch64 The packages in Divide the short-resulting list will be divided up between the members of the class for further analysis.
(There are two videos about '''Please see the challenge, both of which are from late 2013 while the program was being finalized: [https://www.youtube.com/watch?v=Lo1dBB3tke8 One of an interview with Maddog and Steve Macintyre[Fall 2014 SPO600 Packages by Participant]], and [http://people.linaro.org/linaro-connect/lcu13/videos/10-28-Monday/LCU13%20ARM%20Performance%20Optimizations.mp4 perform the other of a Linaro Connect presentation by Maddog])steps listed there.'''
{{Admon/tip|Participating in the Linaro Performance Challenge|You are invited to participate in the [http://performance.linaro.org Linaro Performance Challenge] directly, utilizing the work you are doing in the SPO600 course. Doing so may enable you to receive a prize for participation and the chance to win a trip to a Linaro Connect conference. In order to participate in the Challenge, you will need to comply with the technical requirements and rules of the Challenge.<br/><br/>Your participation in this course, and the mark you receive in this course, are independent of your participation in the Linaro Performance Challenge.<br/><br/>In other words: Linaro and Seneca are distinct entities, and although you can participate in both the Challenge and SPO600 with the same project, Seneca assumes no responsibility for your interaction with Linaro, and vice-versa.}}
=== Week 5 Deliverables ===
* Blog about the potential project list [[SPO600 Assembler Lab|assembler lab (Lab 3)]].* Do the tasks assigned to youon the [[Fall 2014 SPO600 Packages by Participant]] page, and blog about it.
<!--== Week 6 ==
== Carried Forward = Tuesday (Oct 7) ===
=== Friday (Jan 17) ===* [[SPO600 Compiled C Lab]]Jon "Maddog" Hall will be joining us for a remote talk and Q&A via Google Hangout.
== Deliverables = Friday (Oct 10) ===* Blog your conclusion to the [[SPO600 Compiled C Lab]]
In groups, we'll be analyzing software pacakges from the [[Fall 2014 SPO600 Packages by Participant|Packages by Participant]] list to find the platform-specific code and build instructions.
=== Week 3 6 Deliverables ===
=== Tuesday * Pick three additional packages (Jan 21not the ones done in class) ===* from your section of the [[Assembler BasicsFall 2014 SPO600 Packages by Participant|Packages by Participant]]list and find the platform-specific code (or build instructions). Figure out what that code does, and document that on the list page. Blog about your results and your reflections on the task.
=== Friday (Jan 24) ===* Background information: [[SPO600 aarch64 QEMU on Ireland]]* [[SPO600 Assembler Lab]] === Week 3 Deliverables ===* Blog your conclusion to the [[SPO600 Assembler Lab]] == Week 4 == === Tuesday (Jan 28) ===* [[SPO600 Assembler Lab|Assembler Lab]] review* [[Inline Assembly Language]]* [[Compiler Optimizations]] === Friday (Jan 31) === * [[Codebase Analysis Lab]] === Week 4 Deliverables === * '''Reminder:''' Week 1-3 blog posts are due for marking on Friday, January 31.* Blog about the [[Codebase Analysis Lab]] == Week 5 7 ==
=== Tuesday (Feb 4Oct 14) ===
Platform-Discussion of some of the reasons that platform specific (usually assembly language) code is often utilized for '''Memory Barriers''' and '''Atomics Operations'''.used in software
==== Memory Barriers ====
** [http://blogs.msdn.com/b/oldnewthing/archive/2008/10/03/8969397.aspx MSDN Blog Post] with a very clear explanation of Acquire-Release.
** [http://preshing.com/20130922/acquire-and-release-fences/ Preshing on Programming post] with a good explanation.
** [http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.genc010197a/index.html ARMv8 Instruction Set Architecture Manual] (ARM InfoCentre registration required) - See the section on Acquire/Release and Load/Store, especially Load/Store Exclusive (e.g., LDREX)
==== Atomics ====
'''Atomics''' are operations which must be completed in a single step (or appear to be completed in a single step) without potential interruption.
* Wikipedia has a good basic overview of the need for atomicity in the article on [http://en.wikipedia.org/wiki/Linearizability Linerarizability]
* GCC provides intrinsics (built-in functions) for atomic operations, as documented in the GCC manual:
** [http://gcc.gnu.org/onlinedocs/gcc-4.8.2/gcc/_005f_005fsync-Builtins.html#_005f_005fsync-Builtins Legacy __sync Built-in Functions for Atomic Memory Access]
** [http://gcc.gnu.org/onlinedocs/gcc-4.8.2/gcc/_005f_005fatomic-Builtins.html#_005f_005fatomic-Builtins Built-in functions for memory model aware atomic operations]
* The Fedora project has some guidelines/recommendations for the use of these GCC builtins:
** http://fedoraproject.org/wiki/Architectures/ARM/GCCBuiltInAtomicOperations
 
=== Friday (Feb 7) ===
==== Hack Session: Potential Project Analysis ====
Select a project from the [[Winter 2014 SPO600 Software List]] and perform these steps:# Edit that page to put your name in the "Claimed by" column.# Investigate the package to determine:#* If the current version has been built for ARM === Friday (e.g., exists in the Fedora aarch64 port - fastest way to test is to use 'yum' inside the arm64 emulation environment on IrelandOct 17)#* What the platform-specific code in the software does#* Whether portable work-arounds exist#* The need for an aarch64 port or for platform-specific code elimination#* Opportunities for optimization#* The amount of work involved in porting and optimizing, and your skills for performing that work# Based on the result of your investigation, decide on your interest in the project.#* If you wish to choose this project for yourself, place it on your row in the [[Winter 2014 SPO600 Participants|Participants]] page.#* If you do not wish to choose this project, remove your name from the "Claimed by" column in the [[Winter 2014 SPO600 Software List|Software List]] page.# Repeat until you have two packages.===
{{Admon/note|Overload|It is strongly recommended that * [[Compiler Intrinsics]]** The use of compiler intrinsics (e.g., those in gcc, or in another compiler) locks you choose two projects with a total scope sum into the use of 0-1that specific compiler (or another that supports the exact same intrinsics), but it provides platform portability. If you wist It is better to try a higher use language features (e.g., C11 or lower sumC++11 atomic and acquire/release syntax) where possible, but since that is often not possible, or the use of compiler intrinsics is more or less maintainable than two projectsinline assembly.** GCC provides intrinsics (built-in functions) for atomic operations, please talk to as documented in the GCC manual:*** [http://gcc.gnu.org/onlinedocs/gcc-4.9.1/gcc/_005f_005fsync-Builtins.html#_005f_005fsync-Builtins Legacy __sync Built-in Functions for Atomic Memory Access]*** [http://gcc.gnu.org/onlinedocs/gcc-4.9.1/gcc/_005f_005fatomic-Builtins.html#_005f_005fatomic-Builtins Built-in functions for memory model aware atomic operations]** The Fedora project has some guidelines/recommendations for the use of these GCC builtins:*** http://fedoraproject.org/wiki/Architectures/ARM/GCCBuiltInAtomicOperations* Select your project(s):** Criteria:**# Interest**# Scope**# Fit between your professorskills and project needs**# Upstream status (e.g.}}, dead project)
{{Admon/tip|RPM Packages|For sofware that is present in the rpmfusion repositories but not in Fedora, you can use <code>yumdownloader --source ''packagename''</code> to grab the source RPM and then examine it using the RPM tools. See [[RPM Packaging Process]] for information.}}=== Week 7 Deliverables ===
=== Week 5 Deliverables ===# Select at least two software packages from the [http://performance.linaro.org Linaro performance web site] and/or the [[Fall 2014 SPO600 Packages by Participant|Packages]] page.# Record your choice on:## The [[Fall 2014 SPO600 Participants|Participants page]] - so that your colleagues in class know that you're working on the package(s). '''Note:''' Package choices will be approved by [[User:Chris Tyler|your professor]], but will usually be accepted on a first-come, first-served basis.## The [http://performance.linaro.org Linaro performance web site] - this will tell other people outside of our group within the Linux-on-ARM community that you are working on the package(s).# Investigate and blog about your choice.
* Blog about your two selected projects, including your detailed initial analysis of them.** You may want to break this into a couple of posts - e.g., post about your first package while you're working on your second.** Feel free to also blog about why you did ''Over reading week:'not''' choose particular # Contact the upstream communities for the packages, too. == Week 6 == === Tuesday (Feb 11) === * Architectureyou have selected --specific code for Performance** Sometimes assembler is used in so that they know that you are working on the package and to open a C/C++ program channel of communication for performance. However, modern versions of C/C++ your forthcoming patches (such as C++11) and recent compilers provide portable ways of accessing high-performance processor capabilities, such as Single Instruction/Multiple Data (SIMD) instructions (called "marketing names" such as SSE, Neon, MMX, 3DNowor benchmarks, or AltaVec on various processorsother results).** Linaro enginener Matthew Gretton-Dann gave # Formulate a good presentation on [http://www.linaro.org/linaro-blog/2013/09/20/introduction-to-porting-and-optimising-code/ Porting and Optimizing Code] for aarch64. The vectorization portion, beginning at 28:10, provides a good introduction to SIMD and autovectorization using GCC on aarch64 (Note that the earlier portion of the presentation includes good information about Atomics).*** [http://www.youtube.com/watch?v=epzYErIIx0Y YouTube Video] direct link*** [http://www.linaro.org/assets/common/campus-party-presentation-Sept_2013.pdf Slides] direct link** Note work plan that will conclude with landing your software changes in the presentation above, Matthew takes upstream software before the code beyond portability without straying into assembler (e.g., using compiler-specific, architecture-specific intrinsics). It is possible to achieve almost all end of the performance gains without becoming arch-specific, and most of those can be attained without becoming compiler-specific as wellcourse.* For full details on the SIMD instructions in aarch64, refer to the [http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.genc010197a/index.html ARMv8 Instruction Set Overview], particularly section 5.7. === Week 6 Deliverables ===* Complete your analysis of your two selected software projects (if you haven't already) - see [[#Week 5|Week 5]]. Blog in detail about your findings.* Identify the upstream communities that develop work plan and maintain the software what you have selected need to work on. Figure out how they are structured, how they communicate, how code is maintained, and how patches are accepted. Introduce yourself investigate/learn in order to each of the two communities (one for each of the two software projects you have selected). Blog about complete your findingsproject== Week 7 ==* Project Work
== Week 8 ==
* Project Work ([[User:Chris Tyler|Chris Tyler]] is at [http://www.linaro.org/connect-lca14 Linaro Connect]) this week.
* Aim at getting your code changes upstream to your communities
 
== Week 9 ==
=== Tuesday (March 11) ===
* Status updates
* Update from Linaro Connect
* Discussion of useful tools
** screen
** time
=== Friday Tuesday (March 14Oct 28) ===* Comparison of Emulation** QEMU** Fast Model and Foundation Model* Install and configure the Foundation Model** [[:fedora:Architectures/ARM/AArch64/QuickStart|Fedora AArch64 Quick Start]]** [http://www.linaro.org/engineering/engineering-projects/armv8 Linaro Foundation Model Instructions]* Baseline Benchmarking
==== Resources ====* Foundation Model** [http://www.arm.com/products/tools/models/fast-models/ ARM Fast Models] - Note that "fast" here refers to Working with the modelling approach, not execution speed!Code* BenchmarkingWorking with GIT** [http://www.tokutek.com/wp-content/uploads/2013/05/20130424-percona-live-benchmarking.pdf Benchmarking Talk by Tim Callaghan]Working with other version control systems
=== Week 9 Deliverables ===* Set up Looking at How Distributions Package the Foundation Model* Upstream your proposed code changesCode* Blog about your workUsing fedpkg
== Week 10 =Friday (Oct 31) ===* Benchmarking and Profiling
=== Tuesday (March 18) ===
* Profiling with <code>gprof</code>
** Build with profiling enabled (use the option <code>-pg</code>with both gcc and ld)
** Run the profile-enabled executable
** Analyze the data in the <code>gmon.out</code> file
* [http://www.thegeekstuff.com/2012/08/gprof-tutorial/ Profiling with GProf]
=== Week 8 Deliverables ===* Blog about your progress connecting with the communities associated with your projects and working with the code. == Week 9 ===== Tuesday (Nov 4) ==* Profiling/baseline benchmarking review* Hacking session === Friday (March 21Nov 7) ===* Gather Hacking session === Week 9 Deliverables ===* Blog about your baseline statistics for benchmarking/profiling. == Week 10 ===== Tuesday (Nov 11) ===* Presentation on your softwareproject status === Friday (Nov 14) ===* Running AArch64 code on x86** Foundation models** [[AArch64 QEMU User Space Emulation]]
=== Week 10 Deliverables ===
* Blog about your baseline benchmark project status  == Week 11 ===== Tuesday (Nov 18) ===* Discussion and hack session** Blog post about upstreaming: [https://www.linaro.org/blog/core-dump/working-upstream/ What do we mean by working upstream: A long-term contributor's view] === Friday (Nov 21) ===* Discussion and hack session === Week 11 Deliverables ===* Upstream your changes/test results/documentation* Blog about your work* '''Note: Blogs will be marked as of Nov 21 11:59 pm''' == Week 12 ===== Tuesday (Nov 25) ===* Project update presentations === Friday (Nov 28) ===* Discussion and hack session: ''Commercial vs. Technical Reality'' == Week 13 == === Tuesday (Dec 2) ===* Discussion and hack session === Friday (Dec 5) ===* Wrap-->up session* '''Remember: Final project submissions via blog are due 11:59 pm December 10.''' 
<BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/><BR/>